Abstract
The Internet of Things is the technology that is exploding in the day-to-day life of the home to the large industrial environment. An IoT connects various applications and services via the internet to make the environment contented. The way of communication among the devices leads to network vulnerability with various attacks. To protect from the security vulnerability of the IoT, the Intrusion Detection Systems (IDS) is employed in the network layer. The network packets from the interconnected IoT applications and services are stored in the Linux server on the end nodes. The packets are got from the server using the crawler into the network layer for attack prediction. Thus, the work contains the main objective is to identify and detect the intrusion among the IoT environment based on machine learning (ML) using the benchmark dataset NSL-KDD. The NSL-KDD dataset is pre-processed to sanitize the null values, eliminating the duplicate and unwanted columns. The cleaned dataset is then assessed to construct the novel custom features and basic features for the attack detection, which represent the feature vector. Novel features are constructed to reduce the learning confusion of machine learning algorithm. The feature vector with the novel and basic features is then processed by employing the feature selection strategy LASSO to get the significant features to increase the prediction accuracy. Due to the outperform of ensembled machine learning algorithms, HSDTKNN (Hybrid Stacking Decision Tree with KNN), HSDTSVM (Hybrid Stacking Decision Tree with SVM) and TCB (Tuned CatBoost) are used for classification. Tuned CatBoost (TCB) technique remarkably predicts the attack that occurs among the packets and generates the alarm. The experimental outcomes established the sufficiency of the proposed model to suits the IoT IDS environment with an accuracy rate of 97.8313%, 0.021687 of error rate, 97.1001% of sensitivity, and specificity of 98.7052%, while prediction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Devaraju S, Ramakrishnan S (2014) Performance comparison for intrusion detection system using neural network with KDD dataset. ICTACT J Soft Comput 4(3):743–752
Phadke A, Kulkarni M, Bhawalkar P, Bhattad R (2019) A review of machine learning methodologies for network ıntrusion detection. In: Third national conference on computing methodologies and communication (ICCMC 2019), pp 272–275
Soni P, Sharma P (2014) An intrusion detection system based on KDD-99 data using data mining techniques and feature selection. Int J Soft Comput Eng (IJSCE) 4(3):1–8
Somwang P, Lilakiatsakun W (2012) Intrusion detection technique by using fuzzy ART on computer network security. In: IEEE—7th IEEE conference on ındustrial electronics and applications (ICIEA)
Horng S-J, Su M-Y, Chen Y-H, Kao T-W, Chen R-J, Lai J-L, Perkasa CD (2011) A novel intrusion detection system based on hierarchical clustering and support vector machines. Exp Syst Appl 38(1):306–313
Ei Boujnouni M, Jedra M (2018) New ıntrusion detection system based on support vector domain description with ınformation metric. Int J Network Secur pp 25–34
Bhumgara A, Pitale A (2019) Detection of network ıntrusions using hybrid ıntelligent system. In: International conferences on advances in ınformation technology, pp 500–506
Sree Kala T, Christy A (2019) An ıntrusion detection system using opposition based particle swarm optimization algorithm and PNN. In: International conference on machine learning, big data, cloud and parallel computing, pp 184–188
Rani D, Kaushal NC (2020) Supervised machine learning based network ıntrusion detection system for ınternet of things. In: 2020 11th ınternational conference on computing, communication and networking technologies (ICCCNT)
Larriva-Novo X, Villagrá VA, Vega-Barbas M, Rivera D, Sanz Rodrigo M (2021) An IoT-focused intrusion detection system approach based on preprocessing characterization for cybersecurity datasets. Sensors 21:656. https://doi.org/10.3390/s21020656
Islam N, Farhin F, Sultana I, Kaiser MS, Rahman MS et al (2021) Towards machine learning based intrusion detection in IoT networks. CMC-Comput Mater Continua 69(2):1801–1821
Sapre S, Ahmadi P, Islam K (2019) A robust comparison of the KDDCup99 and NSL-KDD IoT network ıntrusion detection datasets through various machine learning algorithms
Houichi M, Jaidi F, Bouhoula A (2021) A systematic approach for IoT cyber-attacks detection in smart cities using machine learning techniques. In: Barolli L, Woungang I, Enokido T (eds) Advanced ınformation networking and applications. AINA 2021. Lecture notes in networks and systems, vol 226. Springer, Cham. https://doi.org/10.1007/978-3-030-75075-6_17
Liang C, Shanmugam B, Azam S (2020) Intrusion detection system for the ınternet of things based on blockchain and multi-agent systems. Electronics 9(1120):1–27
Urmila TS, Balasubramanian R (2019) Dynamic multi-layered ıntrusion ıdentification and recognition using artificial ıntelligence framework. Int J Comput Sci Inf Secur (IJCSIS) 17(2):137–147
Rahimunnisa K (2020) LoRa-IoT focused system of defense for equipped troops [LIFE]. J Ubiquitous Comput Commun Technol 2(3):153–177
Sivaganesan D (2021) Performance estimation of sustainable smart farming with blockchain technology. IRO J Sustain Wireless Syst 3(2):97–106. https://doi.org/10.36548/jsws.2021.2.004
Dr PK (2020) A sensor based IoT monitoring system for electrical devices using Blynk framework. J Electron Inform 2(3):182–187
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jeyanthi, D.V., Indrani, B. (2022). Intrusion Detection System Intensive on Securing IoT Networking Environment Based on Machine Learning Strategy. In: Hemanth, D.J., Pelusi, D., Vuppalapati, C. (eds) Intelligent Data Communication Technologies and Internet of Things. Lecture Notes on Data Engineering and Communications Technologies, vol 101. Springer, Singapore. https://doi.org/10.1007/978-981-16-7610-9_11
Download citation
DOI: https://doi.org/10.1007/978-981-16-7610-9_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7609-3
Online ISBN: 978-981-16-7610-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)